Merge pull request #199 from datacite/crossref-reader-fix

Make crossref_reader methods safer

Author: codycooperross

lib/bolognese/readers/crossref_reader.rb

@@ -373,8 +373,8 @@ def crossref_references(bibliographic_metadata)
 
       def crossref_has_translation(program_metadata)
         refs = program_metadata.dig("related_item") if program_metadata.is_a?(Hash)
-        Array.wrap(refs).select { |a| a["intra_work_relation"]["relationship_type"] == "hasTranslation" }.map do |c|
-          if c["intra_work_relation"]["identifier_type"] == "doi"
+        Array.wrap(refs).select { |a| a.dig("intra_work_relation", "relationship_type") == "hasTranslation" }.map do |c|
+          if c.dig("intra_work_relation", "identifier_type") == "doi"
             { "relatedIdentifier" => parse_attributes(c["intra_work_relation"]).downcase,
               "relationType" => "HasTranslation",
               "relatedIdentifierType" => "DOI" }.compact
@@ -386,8 +386,8 @@ def crossref_has_translation(program_metadata)
 
       def crossref_is_translation_of(program_metadata)
         refs = program_metadata.dig("related_item") if program_metadata.is_a?(Hash)
-        Array.wrap(refs).select { |a| a["intra_work_relation"]["relationship_type"] == "isTranslationOf" }.map do |c|
-          if c["intra_work_relation"]["identifier_type"] == "doi"
+        Array.wrap(refs).select { |a| a.dig("intra_work_relation", "relationship_type") == "isTranslationOf" }.map do |c|
+          if c.dig("intra_work_relation", "identifier_type") == "doi"
             { "relatedIdentifier" => parse_attributes(c["intra_work_relation"]).downcase,
               "relationType" => "IsTranslationOf",
               "relatedIdentifierType" => "DOI" }.compact

spec/fixtures/crossref.xml

@@ -64,16 +64,6 @@
                     <surname>Hardtke</surname>
                     <affiliation>Department of Plant Molecular Biology, University of Lausanne, Lausanne, Switzerland</affiliation>
                   </person_name>
-                  <person_name contributor_role="editor" sequence="additional">
-                    <given_name>Ashwini</given_name>
-                    <surname>Sukale</surname>
-                    <affiliation>DataCite</affiliation>
-                  </person_name>
-                  <person_name contributor_role="translator" sequence="additional">
-                    <given_name>Cody</given_name>
-                    <surname>Ross</surname>
-                    <affiliation>DataCite</affiliation>
-                  </person_name>
                 </contributors>
                 <jats:abstract xmlns:jats="http://www.ncbi.nlm.nih.gov/JATS1">
                   <jats:p>Among various advantages, their small size makes model organisms preferred subjects of investigation. Yet, even in model systems detailed analysis of numerous developmental processes at cellular level is severely hampered by their scale. For instance, secondary growth of Arabidopsis hypocotyls creates a radial pattern of highly specialized tissues that comprises several thousand cells starting from a few dozen. This dynamic process is difficult to follow because of its scale and because it can only be investigated invasively, precluding comprehensive understanding of the cell proliferation, differentiation, and patterning events involved. To overcome such limitation, we established an automated quantitative histology approach. We acquired hypocotyl cross-sections from tiled high-resolution images and extracted their information content using custom high-throughput image processing and segmentation. Coupled with automated cell type recognition through machine learning, we could establish a cellular resolution atlas that reveals vascular morphodynamics during secondary growth, for example equidistant phloem pole formation.</jats:p>
@@ -163,14 +153,6 @@
                     <rel:description>Data from: Automated quantitative histology reveals vascular morphodynamics during Arabidopsis hypocotyl secondary growth</rel:description>
                     <rel:inter_work_relation identifier-type="doi" relationship-type="isSupplementedBy">10.5061/dryad.b835k</rel:inter_work_relation>
                   </rel:related_item>
-                  <rel:related_item>
-                    <rel:description>Portuguese translation of an article</rel:description>
-                    <rel:intra_work_relation relationship-type="isTranslationOf" identifier-type="doi">10.5555/original_language</rel:intra_work_relation>
-                  </rel:related_item>
-                  <rel:related_item>
-                    <rel:description>Spanish translation of an article</rel:description>
-                    <rel:intra_work_relation relationship-type="hasTranslation" identifier-type="doi">10.5555/other_language</rel:intra_work_relation>
-                  </rel:related_item>
                 </rel:program>
                 <archive_locations>
                   <archive name="CLOCKSS" />

spec/fixtures/crossref_schema_4.6_values.xml

@@ -62,8 +62,17 @@
                           <affiliation>Brown University</affiliation>
                           <ORCID authenticated="true">https://orcid.org/0000-0002-1825-0097</ORCID>
                       </person_name>
+                      <person_name contributor_role="editor" sequence="additional">
+                        <given_name>Ashwini</given_name>
+                        <surname>Sukale</surname>
+                        <affiliation>DataCite</affiliation>
+                      </person_name>
+                      <person_name contributor_role="translator" sequence="additional">
+                        <given_name>Cody</given_name>
+                        <surname>Ross</surname>
+                        <affiliation>DataCite</affiliation>
+                      </person_name>
                   </contributors>
-                  
                   <publication_date media_type="online">
                       <month>08</month>
                       <day>13</day>

spec/readers/crossref_reader_spec.rb

@@ -1100,7 +1100,7 @@
     end
 
     it "with Schema 4.6 Translator contributor" do
-      input = fixture_path + 'crossref.xml'
+      input = fixture_path + 'crossref_schema_4.6_values.xml'
       subject = Bolognese::Metadata.new(input: input)
 
       expect(subject.contributors).to eq([